Machine Learning
Feature Weighting Improves Pool-Based Sequential Active Learning for Regression
Dongrui Wu
Pool-based sequential active learning for regression (ALR) optimally selects a small number of samples sequentially from a large pool of unlabeled samples to label, so that a more accurate regression model can be constructed under a given labeling budget. Representativeness and diversity, which involve computing the distances among different samples, are important considerations in ALR. However, previous ALR approaches do not incorporate the importance of different features in inter-sample distance computation, resulting in inaccurate distances and hence sub-optimal sample selection. This paper proposes four feature weighted single-task ALR approaches and three feature weighted multi-task ALR approaches, where the ridge regression coefficients trained from a small amount of previously labeled samples are used to weight the corresponding features in inter-sample distance computation. Extensive experiments showed that this intuitive and easy-to-implement enhancement almost always improves the performance of five existing ALR approaches, in both single-task and multi-task regression problems. The feature weighting strategy may also be easily extended to stream-based ALR, and classification
algorithms.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Demographic Parity Tails for Regression
Naht Sinh Le, Christophe Denis and Mohamed Hebiri
Demographic parity (DP) is a widely studied
fairness criterion in regression, enforcing independence between the predictions and sensitive attributes. However, constraining the entire distribution can degrade predictive accuracy and may be unnecessary for many applications, where
fairness concerns are localized to specific regions of the distribution. To overcome this issue, we propose a new framework for regression under DP that focuses on the tails of target distribution across sensitive groups. Our methodology builds on optimal transport theory. By enforcing
fairness constraints only over targeted regions of the distribution, our approach enables more nuanced and context-sensitive interventions. Leveraging recent advances, we develop an interpretable and flexible
algorithm that leverages the
geometric structure of optimal transport. We provide theoretical guarantees, including risk bounds and
fairness properties, and validate the method through experiments in regression settings.
Read the full abstract ▾
Machine Learning
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
Rafael Pardinas, Ehsan Kamalloo, David Vazquez et al. (+1 more)
Building general-purpose
reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted by frontier open-weight models. However, their training recipes and domain mixtures are often not disclosed. Joint optimization across domains poses significant challenges: domains vary widely in rollout length, problem difficulty, and sample efficiency. Further, models with long chain-of-thought traces increase inference cost and latency, making efficiency critical for practical deployment. We present Apriel-Reasoner, trained with a reproducible multi-domain RL post-training recipe on Apriel-Base, a 15B-parameter open-weight LLM, across five domains using public
datasets: mathematics, code generation, instruction following, logical puzzles, and function calling. We introduce adaptive domain sampling that preserves target completed-rollout ratios despite heterogeneous rollout dynamics, and a difficulty-aware length penalty that, at no additional training overhead, encourages longer
reasoning for difficult problems and shorter traces for easy ones. Trained with a strict 16K-
token output budget, Apriel-Reasoner remains effective at a 32K output budget and improves over Apriel-Base on AIME 2025, GPQA, MMLU-Pro, and LiveCodeBench while producing 30-50% shorter
reasoning traces. Among the evaluated open-weight models of similar scale, it improves the accuracy-
token tradeoff using a fully public-data recipe.
Read the full abstract ▾
All authors Rafael Pardinas, Ehsan Kamalloo, David Vazquez, Alexandre Drouin
Machine Learning · Cross-listed from cs.CV
Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models
Antoine Saporta, Baptiste Callard, Corentin Dancette et al. (+5 more)
The rapid growth of medical imaging has fueled the development of Foundation Models (FMs) to reduce the growing, unsustainable workload on radiologists. While recent FMs have shown the power of large-scale pre-training to CT and MRI analysis, there remains significant room to optimize how these models learn from complex radiological volumes. Building upon the Curia framework, this work introduces Curia-2, which significantly improves the original pre-training strategy and representation quality to better capture the specificities of radiological data. The proposed methodology enables scaling the architecture up to billion-parameter
Vision Transformers, marking a first for multi-modal CT and MRI FMs. Furthermore, we formalize the evaluation of these models by extending and restructuring CuriaBench into two distinct tracks: a 2D track tailored for slice-based
vision models and a 3D track for volumetric benchmarking. Our results demonstrate that Curia-2 outperforms all FMs on
vision-focused tasks and fairs competitively to
vision-
language models on clinically complex tasks such as finding detection. Weights will be made publicly available to foster further research.
Read the full abstract ▾
All authors Antoine Saporta, Baptiste Callard, Corentin Dancette, Julien Khlaut, Charles Corbière, Leo Butsanets, Amaury Prat, Pierre Manceron
Machine Learning
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
Yuejiang Liu, Fan Feng, Lingjing Kong et al. (+6 more)
General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning which primarily focuses on optimal actions, a world model needs to be reliable over a vast space of suboptimal actions, which are often underrepresented in action-labeled
robot interactions. To address this challenge, we propose World Action Verifier (WAV), a framework that enables world models to identify their own prediction errors and self-improve. The key idea is to decompose action-conditioned state prediction into two independently verifiable factors: state plausibility and action reachability. We show that verifying these factors is significantly more tractable than direct forward prediction due to two underlying asymmetries: the broader availability of action-free data and the lower dimensionality of action-relevant features. Leveraging these asymmetries, we augment a world model with (i) a diverse subgoal generator obtained from
video corpora and (ii) a sparse inverse model that infers actions from a subset of state features. By enforcing cycle consistency among proposed subgoals, inferred actions, and forward rollouts, WAV provides an effective verification mechanism in under-explored regimes, where existing methods often fail. Across nine tasks spanning MiniGrid, RoboMimic, and ManiSkill, our method achieves 2x higher sample efficiency while improving downstream policy performance by over 22%.
Read the full abstract ▾
All authors Yuejiang Liu, Fan Feng, Lingjing Kong, Weifeng Lu, Jinzhou Tang, Kun Zhang, Kevin Murphy, Chelsea Finn, Yilun Du
Machine Learning · Cross-listed from math.PR
Hugo Koubbi, Borjan Geshkovski and Philippe Rigollet
We study a random model of deep multi-head self-
attention in which the weights are resampled independently across layers and heads, as at initialization of training. Viewing depth as a time variable, the residual stream defines a discrete-time interacting particle system on the unit sphere. We prove that, under suitable joint scalings of the depth, the residual step size, and the number of heads, this dynamics admits a nontrivial homogenized limit. Depending on the scaling, the limit is either deterministic or
stochastic with common noise; in the mean-field regime, the latter leads to a
stochastic nonlinear Fokker–Planck equation for the conditional law of a representative
token. In the Gaussian setting, the limiting drift vanishes, making the homogenized dynamics explicit enough to study representation collapse. This yields quantitative trade-offs between dimension, context length, and temperature, and identifies regimes in which clustering can be mitigated.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale
Ayush Garg, Sophia Hager, Jacob Montiel et al. (+5 more)
Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures (CVEs) far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000 new vulnerabilities, motivating the need for automation. We present RuleForge, an AWS internal system that automatically generates detection rules–JSON-based patterns that identify malicious HTTP requests exploiting specific vulnerabilities–from structured
Nuclei templates describing CVE details.
Nuclei templates provide standardized, YAML-based vulnerability descriptions that serve as the structured input for our rule generation process. This paper focuses on RuleForge's architecture and operational deployment for CVE-related threat detection, with particular emphasis on our novel LLM-as-a-judge (Large
Language Model as judge) confidence validation system and systematic feedback integration mechanism. This validation approach evaluates candidate rules across two dimensions–sensitivity (avoiding false negatives) and specificity (avoiding false positives)–achieving AUROC of 0.75 and reducing false positives by 67% compared to synthetic-test-only validation in production. Our 5x5 generation strategy (five parallel candidates with up to five refinement attempts each) combined with continuous feedback loops enables systematic quality improvement. We also present extensions enabling rule generation from unstructured data sources and demonstrate a proof-of-concept agentic workflow for multi-event-type detection. Our lessons learned highlight critical considerations for applying LLMs to cybersecurity tasks, including overconfidence mitigation and the importance of domain expertise in both
prompt design and quality review of generated rules through human-in-the-loop validation.
Read the full abstract ▾
All authors Ayush Garg, Sophia Hager, Jacob Montiel, Aditya Tiwari, Michael Gentile, Zach Reavis, David Magnotti, Wayne Fullen
Machine Learning · Cross-listed from cs.AI
Abnormal Head Movements in Neurological Conditions: A Knowledge-Based Dataset with Application to Cervical Dystonia
Saja Al-Dabet, Sherzod Turaev and Nazar Zaki
Abnormal head movements (AHMs) manifest across a broad spectrum of neurological disorders; however, the absence of a multi-condition resource integrating kinematic measurements, clinical severity scores, and patient demographics constitutes a persistent barrier to the development of AI-driven diagnostic tools. To address this gap, this study introduces NeuroPose-AHM, a knowledge-based
dataset of neurologically induced AHMs constructed through a multi-LLM extraction framework applied to 1,430 peer-reviewed publications. The
dataset contains 2,756 patient-group-level records spanning 57 neurological conditions, derived from 846 AHM-relevant papers. Inter-LLM reliability analysis confirms robust extraction performance, with study-level classification achieving strong agreement (kappa = 0.822). To demonstrate the
dataset's analytical utility, a four-task framework is applied to cervical dystonia (CD), the condition most directly defined by pathological head movement. First, Task 1 performs multi-label AHM type classification (F1 = 0.856). Task 2 constructs the Head-Neck Severity Index (HNSI), a unified metric that normalizes heterogeneous clinical rating scales. The clinical relevance of this index is then evaluated in Task 3, where HNSI is validated against real-world CD patient data, with aligned severe-band proportions (6.7%) providing a preliminary plausibility indication for index calibration within the high severity range. Finally, Task 4 performs bridge analysis between movement-type probabilities and HNSI scores, producing significant correlations (p less than 0.001). These results demonstrate the analytical utility of NeuroPose-AHM as a structured, knowledge-based resource for neurological AHM research. The NeuroPose-AHM
dataset is publicly available on Zenodo (https://doi.org/10.5281/zenodo.19386862).
Read the full abstract ▾
Machine Learning
Generalization Bounds and Statistical Guarantees for Multi-Task and Multiple Operator Learning with MNO Networks
Adrien Weihs and Hayden Schaeffer
Multiple operator learning concerns learning operator families $\{G[\alpha]:U\to V\}_{\alpha\in W}$ indexed by an operator descriptor $\alpha$. Training data are collected hierarchically by sampling operator instances $\alpha$, then input functions $u$ per instance, and finally evaluation points $x$ per input, yielding noisy observations of $G[\alpha][u](x)$. While recent work has developed expressive multi-task and multiple operator learning architectures and approximation-theoretic scaling laws, quantitative statistical generalization guarantees remain limited. We provide a covering-number-based generalization analysis for separable models, focusing on the Multiple Neural Operator (MNO) architecture: we first derive explicit metric-
entropy bounds for hypothesis classes given by linear combinations of products of deep ReLU subnetworks, and then combine these complexity bounds with approximation guarantees for MNO to obtain an explicit approximation-estimation tradeoff for the expected test error on new (unseen) triples $(\alpha,u,x)$. The resulting bound makes the dependence on the hierarchical sampling budgets $(n_\alpha,n_u,n_x)$ transparent and yields an explicit learning-rate statement in the operator-sampling budget $n_\alpha$, providing a sample-complexity characterization for generalization across operator instances. The structure and architecture can also be viewed as a general purpose solver or an example of a "small” PDE foundation model, where the triples are one form of multi-modality.
Read the full abstract ▾
Machine Learning
Autolearn: Learn by Surprise, Commit by Proof
Kang-Sin Choi
We propose Autolearn, a framework that enables
language models to learn from documents they read, with no external supervision. Passages that produce anomalously high per-
token loss are flagged, verified through a self-generated Q&A chain, and trained on with conviction-proportional $\beta_2$ adjustment. We introduce the perturbation gap (paraphrase-to-original perplexity ratio) as a metric that distinguishes memorization from understanding. The key mechanism is the training data format: Q&A-format training drives the perturbation gap below the pre-trained baseline (2.098 vs. 2.204, $\Delta = -0.106$, $> 10\sigma$), suppressing
token-sequence memorization, while standard fine-tuning's best attempt remains within noise ($\Delta = -0.010$, $< 1\sigma$). Across four models spanning Qwen3 and Phi-4 families, Autolearn is the only method that enters this regime.
Stochastic evaluation reveals passage-specific knowledge acquisition: the probability of generating a correct novel fact rises from 6% to 54% after training ($p < 10^{-4}$), and Q&A format outperforms standard fine-tuning on genuinely novel facts. The system is self-extinguishing: learned content reduces surprisal below threshold and is skipped on re-encounter.
Read the full abstract ▾
Machine Learning
annbatch unlocks terabyte-scale training of biological data in anndata
Ilan Gold, Felix Fischer, Lucas Arnoldt et al. (+2 more)
The scale of biological
datasets now routinely exceeds system
memory, making data access rather than model computation the primary bottleneck in training machine-learning models. This bottleneck is particularly acute in biology, where widely used community data formats must support heterogeneous metadata, sparse and dense assays, and downstream analysis within established computational ecosystems. Here we present annbatch, a mini-batch loader native to anndata that enables out-of-core training directly on disk-backed
datasets. Across single-
cell transcriptomics, microscopy and whole-genome sequencing
benchmarks, annbatch increases loading throughput by up to an order of magnitude and shortens training from days to hours, while remaining fully compatible with the scverse ecosystem. Annbatch establishes a practical data-loading infrastructure for scalable biological AI, allowing increasingly large and diverse
datasets to be used without abandoning standard biological data formats. Github: https://github.com/scverse/annbatch
Read the full abstract ▾
All authors Ilan Gold, Felix Fischer, Lucas Arnoldt, F. Alexander Wolf, Fabian J. Theis
Machine Learning
PAC-Bayesian Reward-Certified Outcome Weighted Learning
Yuya Ishikawa and Shu Tamano
Estimating optimal individualized treatment rules (ITRs) via outcome weighted learning (OWL) often relies on observed rewards that are noisy or optimistic proxies for the true latent utility. Ignoring this reward uncertainty leads to the selection of policies with inflated apparent performance, yet existing OWL frameworks lack the finite-sample guarantees required to systematically embed such uncertainty into the learning objective. To address this issue, we propose PAC-
Bayesian Reward-Certified Outcome Weighted Learning (PROWL). Given a one-sided uncertainty certificate, PROWL constructs a conservative reward and a strictly policy-dependent lower bound on the true expected value. Theoretically, we prove an exact certified reduction that transforms robust policy learning into a unified, split-free cost-sensitive classification task. This formulation enables the derivation of a nonasymptotic PAC-Bayes lower bound for randomized ITRs, where we establish that the optimal posterior maximizing this bound is exactly characterized by a general Bayes update. To overcome the learning-rate selection problem inherent in generalized
Bayesian inference, we introduce a fully automated, bounds-based calibration procedure, coupled with a Fisher-consistent certified hinge surrogate for efficient optimization. Our experiments demonstrate that PROWL achieves improvements in estimating robust, high-value treatment regimes under severe reward uncertainty compared to standard methods for ITR estimation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NI
Physics-Informed Transformer for Multi-Band Channel Frequency Response Reconstruction
Anatolij Zubow, Joana Angjo, Sigrid Dimce et al. (+1 more)
Wideband channel frequency response (CFR) estimation is challenging in multi-band wireless systems, especially when one or more sub-bands are temporarily blocked by co-channel interference. We present a physics-informed complex
Transformer that reconstructs the full wideband CFR from such fragmented, partially observed spectrum snapshots. The interference pattern in each sub-band is modeled as an independent two-state discrete-time Markov chain, capturing realistic bursty occupancy behavior. Our model operates on the joint time-frequency grid of $T$ snapshots and $F$ frequency bins and uses a factored self-
attention mechanism that separately attends along both axes, reducing the computational complexity to $O(TF^2 + FT^2)$. Complex-valued inputs and outputs are processed through a holomorphic linear layer that preserves phase relationships. Training uses a composite physics-informed loss combining spectral fidelity, power delay profile (PDP) reconstruction, channel impulse response (CIR) sparsity, and temporal smoothness. Mobility effects are incorporated through per-sample velocity randomization, enabling generalization across different mobility regimes. Evaluation against three classical baselines, namely, last-observation-carry-forward, zero-fill, and cubic-spline interpolation, shows that our approach achieves the highest PDP similarity with respect to the ground truth, reaching $\rho \geq 0.82$ compared to $\rho \geq 0.62$ for the best baseline at interference occupancy levels up to 50%. Furthermore, the model degrades smoothly across the full velocity range, consistently outperforming all other baselines.
Read the full abstract ▾
All authors Anatolij Zubow, Joana Angjo, Sigrid Dimce, Falko Dressler
Machine Learning · Cross-listed from stat.ML
A Novel Theoretical Analysis for Clustering Heteroscedastic Gaussian Data without Knowledge of the Number of Clusters
Dominique Pastor, Elsa Dupraz, Ismail Hbilou et al. (+1 more)
This paper addresses the problem of clustering measurement vectors that are heteroscedastic in that they can have different covariance
matrices. From the assumption that the measurement vectors within a given cluster are Gaussian distributed with possibly different and unknown covariant
matrices around the cluster centroid, we introduce a novel cost function to estimate the centroids. The zeros of the gradient of this cost function turn out to be the fixed-points of a certain function. As such, the approach generalizes the methodology employed to derive the existing Mean-Shift
algorithm. But as a main and novel theoretical result compared to Mean-Shift, this paper shows that the sole fixed-points of the identified function tend to be the cluster centroids if both the number of measurements per cluster and the distances between centroids are large enough. As a second contribution, this paper introduces the Wald kernel for clustering. This kernel is defined as the p-value of the Wald hypothesis test for testing the mean of a Gaussian. As such, the Wald kernel measures the plausibility that a measurement vector belongs to a given cluster and it scales better with the dimension of the measurement vectors than the usual Gaussian kernel. Finally, the proposed theoretical framework allows us to derive a new clustering
algorithm called CENTRE-X that works by estimating the fixed-points of the identified function. As Mean-Shift, CENTRE-X requires no prior knowledge of the number of clusters. It relies on a Wald hypothesis test to significantly reduce the number of fixed points to calculate compared to the Mean-Shift
algorithm, thus resulting in a clear gain in complexity. Simulation results on synthetic and real data sets show that CENTRE-X has comparable or better performance than standard clustering
algorithms K-means and Mean-Shift, even when the covariance
matrices are not perfectly known.
Read the full abstract ▾
All authors Dominique Pastor, Elsa Dupraz, Ismail Hbilou, Guillaume Ansel
Machine Learning · Cross-listed from cs.AI
Probabilistic classification from possibilistic data: computing Kullback-Leibler projection with a possibility distribution
Ismaïl Baaj and Pierre Marquis
We consider learning with possibilistic supervision for multi-class classification. For each training instance, the supervision is a normalized possibility distribution that expresses graded plausibility over the classes. From this possibility distribution, we construct a non-empty closed convex set of admissible probability distributions by combining two requirements: probabilistic compatibility with the possibility and necessity measures induced by the possibility distribution, and linear shape constraints that must be satisfied to preserve the qualitative structure of the possibility distribution. Thus, classes with the same possibility degree receive equal probabilities, and if a class has a strictly larger possibility degree than another class, then it receives a strictly larger probability. Given a strictly positive probability vector output by a model for an instance, we compute its Kullback-Leibler projection onto the admissible set. This projection yields the closest admissible probability distribution in Kullback-Leibler sense. We can then train the model by minimizing the divergence between the prediction and its projection, which quantifies the smallest adjustment needed to satisfy the induced dominance and shape constraints. The projection is computed with Dykstra's
algorithm using Bregman projections associated with the negative
entropy, and we provide explicit formulas for the projections onto each constraint set. Experiments conducted on synthetic data and on a real-world natural
language inference task, based on the ChaosNLI
dataset, show that the proposed projection
algorithm is efficient enough for practical use, and that the resulting projection-based learning objective can improve predictive performance.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Woosh: A Sound Effects Foundation Model
Gaëtan Hadjeres, Marc Ferras, Khaled Koutini et al. (+7 more)
The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio
alignment model for conditioning, together with (3) text-to-audio and (4)
video-to-audio generative models. Distilled text-to-audio and
video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.
Read the full abstract ▾
All authors Gaëtan Hadjeres, Marc Ferras, Khaled Koutini, Benno Weck, Alexandre Bittar, Thomas Hummel, Zineb Lahrichi, Hakim Missoum, Joan Serrà, Yuki Mitsufuji
Machine Learning · Cross-listed from cs.CV
On Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Measurements
George Sebastian, Philipp Berthold, Bianca Forkel et al. (+2 more)
Automotive radar perception pipelines commonly construct angle-domain representations via beamforming before applying learning-based models. This work instead investigates a representational question: can meaningful spatial structure be learned directly from pre-beamforming per-
antenna range-Doppler (RD) measurements? Experiments are conducted on a 6-TX x 8-RX (48 virtual
antennas) commodity automotive radar employing an A/B chirp-sequence frequency-modulated continuous-wave (CS-FMCW) transmit scheme, in which the effective transmit aperture varies between chirps (single-TX vs multi-TX), enabling controlled analyses of chirp-dependent transmit configurations. We operate on pre-beamforming per-
antenna RD tensors using a dual-chirp shared-weight encoder trained in an end-to-end, fully data-driven manner, and evaluate spatial recoverability using bird's-eye-view (BEV) occupancy as a
geometric probe rather than a performance-driven objective. Supervision is visibility-aware and cross-modal, derived from
LiDAR with explicit modeling of the radar field-of-view and occlusion-aware
LiDAR observability via ray-based visibility. Through analyses of signal properties, transmit configurations (A-only, B-only, and A+B), receive aperture, and range-Doppler structure, together with physics-aligned baselines, we investigate the factors influencing spatial recoverability. The results indicate that meaningful spatial structure is recoverable from pre-beamforming per-
antenna RD tensors under the studied A/B CS-FMCW radar configuration through learned spatial mixing, without relying on hand-crafted signal-processing stages.
Read the full abstract ▾
All authors George Sebastian, Philipp Berthold, Bianca Forkel, Leon Pohl, Mirko Maehlisch
Machine Learning
The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
Zihao Wu, Hongyao Tang, Yi Ma et al. (+3 more)
Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity, which impairs the ability to adapt to new data and learn continually. Unfortunately, our understanding of how plasticity loss arises, dissipates, and can be dissolved remains limited to empirical findings, leaving the theoretical end underexplored.To address this gap, we study the plasticity loss problem from the theoretical perspective of network optimization. By formally characterizing the two culprit factors in online RL process: the non-stationarity of data distributions and the non-stationarity of targets induced by bootstrapping, our theory attributes the loss of plasticity to two mechanisms: the rank collapse of the Neural Tangent Kernel (NTK) Gram
matrix and the $\Theta(\frac{1}{k})$ decay of gradient magnitude. The first mechanism echoes prior empirical findings from the theoretical perspective and sheds light on the effects of existing methods, e.g., network reset,
neuron recycle, and noise injection. Against this backdrop, we focus primarily on the second mechanism and aim to alleviate plasticity loss by addressing the gradient attenuation issue, which is orthogonal to existing methods. We propose Sample Weight Decay – a lightweight method to restore gradient magnitude, as a general remedy to plasticity loss for deep RL methods based on experience replay. In experiments, we evaluate the efficacy of \methodName upon TD3, \myadded{Double DQN} and SAC with SimBa architecture in MuJoCo, \myadded{ALE} and DeepMind Control Suite tasks. The results demonstrate that \methodName effectively alleviates plasticity loss and consistently improves learning performance across various configurations of deep RL
algorithms, UTD, network architectures, and environments, achieving SOTA performance on challenging DMC
Humanoid tasks.
Read the full abstract ▾
All authors Zihao Wu, Hongyao Tang, Yi Ma, Jiashun Liu, Yan Zheng, Jianye Hao
Machine Learning
Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling
Aleksei Khalin, Ekaterina Zaychenkova, Aleksandr Yugay et al. (+4 more)
Artificial intelligence (AI) systems accelerate medical workflows and improve diagnostic accuracy in healthcare, serving as second-opinion systems. However, the unpredictability of AI errors poses a significant challenge, particularly in healthcare contexts, where mistakes can have severe consequences. A widely adopted safeguard is to pair predictions with uncertainty estimation, enabling human experts to focus on high-risk cases while streamlining routine verification. Current uncertainty estimation methods, however, remain limited, particularly in quantifying aleatoric uncertainty, which arises from data ambiguity and noise. To address this, we propose a novel approach that leverages disagreement in expert responses to generate targets for training machine learning models. These targets are used in conjunction with standard data labels to estimate two components of uncertainty separately, as given by the law of total variance, via a two-ensemble approach, as well as its lightweight variant. We validate our method on binary image classification, binary and multi-class image
segmentation, and multiple-choice question answering. Our experiments demonstrate that incorporating expert knowledge can enhance uncertainty estimation quality by $9\%$ to $50\%$ depending on the task, making this source of information invaluable for the construction of risk-aware AI systems in healthcare applications.
Read the full abstract ▾
All authors Aleksei Khalin, Ekaterina Zaychenkova, Aleksandr Yugay, Andrey Goncharov, Sergey Korchagin, Alexey Zaytsev, Egor Ershov
Machine Learning
LI-DSN: A Layer-wise Interactive Dual-Stream Network for EEG Decoding
Chenghao Yue, Zhiyuan Ma, Zhongye Xia et al. (+4 more)
Electroencephalography (
EEG) provides a non-invasive window into
brain activity, offering high temporal resolution crucial for understanding and interacting with neural processes through
brain-computer interfaces (BCIs). Current dual-stream neural networks for
EEG often process temporal and spatial features independently through parallel branches, delaying their integration until a final, late-stage fusion. This design inherently leads to an "information silo" problem, precluding intermediate cross-stream refinement and hindering spatial-temporal decompositions essential for full feature utilization. We propose LI-DSN, a layer-wise interactive dual-stream network that facilitates progressive, cross-stream communication at each layer, thereby overcoming the limitations of late-fusion paradigms. LI-DSN introduces a novel Temporal-Spatial Integration
Attention (TSIA) mechanism, which constructs a Spatial Affinity Correlation
Matrix (SACM) to capture inter-electrode spatial structural relationships and a Temporal Channel Aggregation
Matrix (TCAM) to integrate cosine-gated temporal dynamics under spatial guidance. Furthermore, we employ an adaptive fusion strategy with learnable channel weights to optimize the integration of dual-stream features. Extensive experiments across eight diverse
EEG datasets, encompassing motor imagery (MI) classification,
emotion recognition, and steady-state visual evoked potentials (SSVEP), consistently demonstrate that LI-DSN significantly outperforms 13 state-of-the-art (SOTA) baseline models, showcasing its superior robustness and decoding performance. The code will be publicized after acceptance.
Read the full abstract ▾
All authors Chenghao Yue, Zhiyuan Ma, Zhongye Xia, Xinche Zhang, Yisi Zhang, Xinke Shen, Sen Song
Machine Learning
DDCL-INCRT: A Self-Organising Transformer with Hierarchical Prototype Structure (Theoretical Foundations)
Giansalvo Cirrincione
Modern neural networks of the
transformer family require the practitioner to decide, before training begins, how many
attention heads to use, how deep the network should be, and how wide each component should be. These decisions are made without knowledge of the task, producing architectures that are systematically larger than necessary: empirical studies find that a substantial fraction of heads and layers can be removed after training without performance loss. This paper introduces DDCL-INCRT, an architecture that determines its own structure during training. Two complementary ideas are combined. The first, DDCL (Deep Dual Competitive Learning), replaces the feedforward block with a dictionary of learned prototype vectors representing the most informative directions in the data. The prototypes spread apart automatically, driven by the training objective, without explicit regularisation. The second, INCRT (Incremental
Transformer), controls the number of heads: starting from one, it adds a new head only when the directional information uncaptured by existing heads exceeds a threshold. The main theoretical finding is that these two mechanisms reinforce each other: each new head amplifies prototype separation, which in turn raises the signal triggering the next addition. At convergence, the network self-organises into a hierarchy of heads ordered by representational granularity. This hierarchical structure is proved to be unique and minimal, the smallest architecture sufficient for the task, under the stated conditions. Formal guarantees of stability, convergence, and
pruning safety are established throughout. The architecture is not something one designs. It is something one derives.
Read the full abstract ▾
Machine Learning
ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
Zhuolong Li, Boxue Yang and Haopeng Chen
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that graph-level fusion can incur irreducible regret on mixed graphs with separated node-wise spectral preferences. Motivated by this result, we propose ASPECT, a spectral graph contrastive learning method that adaptively fuses low- and high-frequency views at the node level. ASPECT learns a node-wise spectral policy and regularizes it using channel-wise contrastive evidence, enabling different nodes to use different spectral mixtures. We further introduce ASPECT-S, an optional stability-aware extension that uses generated graph-structure and feature perturbations to obtain empirical channel-wise sensitivity estimates, together with a Rayleigh-based spectral search bias for producing informative perturbations. Experiments on homophilic and heterophilic
benchmarks show that ASPECT improves representation quality over competitive spectral and graph contrastive baselines, while ASPECT-S further improves performance under joint graph-structure and feature perturbations.
Read the full abstract ▾
Machine Learning
Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler
Yiran Ma, Jerome Le Ny, Zhichao Chen et al. (+1 more)
In modern process industries, data-driven models are important tools for real-time monitoring when key performance indicators are difficult to measure directly. While accurate predictions are essential, reliable uncertainty quantification (UQ) is equally critical for safety, reliability, and decision-making, but remains a major challenge in current data-driven approaches. In this work, we introduce a
diffusion-based posterior sampling framework that inherently produces well-calibrated predictive uncertainty via faithful posterior sampling, eliminating the need for post-hoc calibration. In extensive evaluations on synthetic distributions, the Raman-based phenylacetic acid soft sensor
benchmark, and a real ammonia synthesis case study, our method achieves practical improvements over existing UQ techniques in both uncertainty calibration and predictive accuracy. These results highlight
diffusion samplers as a principled and scalable paradigm for advancing uncertainty-aware modeling in industrial applications.
Read the full abstract ▾
All authors Yiran Ma, Jerome Le Ny, Zhichao Chen, Zhihuan Song
Machine Learning
CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift
HyunGi Kim, Jisoo Mok, Hyungyu Lee et al. (+2 more)
Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and cause severe performance degradation in pre-trained anomaly detector. Test-time adaptation (TTA) updates a pre-trained model on-the-fly using only unlabeled test data, making it promising for addressing this challenge. In this study, we propose CANDI (Curated test-time adaptation for multivariate time-series ANomaly detection under DIstribution shift), a novel TTA framework that selectively identifies and adapts to potential false positives while preserving pre-trained knowledge. CANDI introduces a False Positive Mining (FPM) strategy to curate adaptation samples based on anomaly scores and latent similarity, and incorporates a plug-and-play Spatiotemporally-Aware Normality Adaptation (SANA) module for structurally informed model updates. Extensive experiments demonstrate that CANDI significantly improves the performance of MTSAD under distribution shift, improving AUROC up to 14% while using fewer adaptation samples.
Read the full abstract ▾
All authors HyunGi Kim, Jisoo Mok, Hyungyu Lee, Juhyeon Shin, Sungroh Yoon
Machine Learning · Cross-listed from cs.CV
Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images
Jamie S. J. Stirling, Noura Al-Moubayed and Hubert P. H. Shum
Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive or
diffusion-based priors to model their dependencies at sample time. In this work, we ask whether positional information is necessary for discrete representations of spatially aligned data. We propose the permutation-invariant vector-quantized autoencoder (PI-VQ), in which latent codes are constrained to carry no positional information. We find that this constraint encourages codes to capture global, semantic features, and enables direct interpolation between images without a learned prior. To address the reduced information capacity of permutation-invariant representations, we introduce matching quantization, a vector quantization
algorithm based on optimal bipartite matching that increases effective bottleneck capacity by $3.5\times$ relative to naive nearest-neighbour quantization. The compositional structure of the learned codes further enables interpolation-based sampling, allowing synthesis of novel images in a single forward pass. We evaluate PI-VQ on CelebA, CelebA-HQ and FFHQ, obtaining competitive precision, density and coverage metrics for images synthesised with our approach. We discuss the trade-offs inherent to position-free representations, including separability and interpretability of the latent codes, pointing to numerous directions for future work.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
Yaxin Luo and Zhiqiang Shen
The ratio of outlier parameters in
language pre-training models and
vision pre-training models differs significantly, making cross-modality (
language and
vision) inherently more challenging than cross-domain adaptation. As a result, many prior studies have focused on cross-domain transfer rather than attempting to bridge
language and
vision modalities, assuming that
language pre-trained models are unsuitable for downstream visual tasks due to disparate parameter spaces. Contrary to this assumption, we show that adding a bridge training stage as a modality adaptation learner can effectively align Large
Language Model (LLM) parameters with
vision tasks. Specifically, we propose a simple yet powerful solution random label bridge training that requires no manual labeling and helps LLM parameters adapt to
vision foundation tasks. Moreover, our findings reveal that partial bridge training is often advantageous, as certain layers in LLMs exhibit strong foundational properties that remain beneficial even without fine-tuning for visual tasks. This surprising discovery opens up new avenues for leveraging
language pre-trained parameters directly within
vision models and highlights the potential of partial bridge training as a practical pathway to cross-modality adaptation.
Read the full abstract ▾
Machine Learning
Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids
Pantelis Dogoulis and Maxime Cordy
Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system's physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post action overload risk of feasible
topology actions. These predictions are used to construct a physics-informed Gibbs prior that both selects a small state-dependent candidate set and reweights policy logits before action selection. In this way, our method reduces exploration difficulty and online simulation cost while preserving the flexibility of a learned policy. We evaluate the approach in three realistic
benchmark environments of increasing difficulty. Across all settings, the proposed method achieves a strong balance between control quality and computational efficiency: it matches oracle-level performance while being approximately $6\times$ faster on the first
benchmark, reaches $94.6\%$ of oracle reward with roughly $200\times$ lower decision time on the second one, and on the most challenging
benchmark improves over a PPO baseline by up to $255\%$ in reward and $284\%$ in survived steps while remaining about $2.5\times$ faster than a strong specialized engineering baseline. These results show that our method provides an effective mechanism for
topology control in power grids.
Read the full abstract ▾
Machine Learning
Real-Time Sensing of Inaccessible Physical Fields via an Edge-Deployable Hardware-Portable Graph Neural Operator
William Howes, Jason Yoo, Kazuma Kobayashi et al. (+4 more)
Real-time inference of inaccessible interior physical fields from sparse boundary observations is a fundamental but unresolved problem in scientific machine learning, with direct relevance to safety-critical monitoring across many engineering applications. Existing neural operators achieve high accuracy but leave deployment to embedded edge platforms unaddressed. Here we introduce VIRSO (Virtual Irregular Real-Time Sparse Operator), the first neural operator with a unique spatial-spectral architecture that explicitly addresses edge-deployment hardware. VIRSO learns a nonlinear mapping from sparse, geometrically disjoint boundary inputs to spatially continuous interior multiphysics fields on irregular unstructured meshes through a spectral-spatial decomposition explicitly aligned with hardware execution: a compute-bound graph spectral pathway and a
memory-bandwidth-bound spatial-aggregation pathway, each independently characterized on datacenter and embedded accelerators. The design reduces the inference energy-delay product by 29$\times$ relative to the vanilla graph-operator baseline (206 J$\cdot$ms $\to$ 7.0 J$\cdot$ms on an NVIDIA H200) and enables 17.0 samples/s embedded inference on an NVIDIA Jetson Orin Nano within 7.06 W board-level power, without modification. A mesh-density-adaptive graph construction strategy (V-KNN) simultaneously improves accuracy and reduces graph edge count by 34%. Across three
benchmarks with reconstruction ratios from 47:1 to 156:1, VIRSO achieves mean relative $L_2$ errors below 1% with fewer parameters than operator baselines and delivers an inference speedup of $\approx 10^4$ times over the high-fidelity reference solver. To our knowledge, this is the first demonstration of a single-digit-watt neural operator, establishing hardware co-design as a missing ingredient in operator-based inference and a tractable path to real-time deployment.
Read the full abstract ▾
All authors William Howes, Jason Yoo, Kazuma Kobayashi, Subhankar Sarkar, Farid Ahmed, Souvik Chakraborty, Syed Bahauddin Alam
Machine Learning · Cross-listed from stat.ML
Learning in Prophet Inequalities with Noisy Observations
Jung-hun Kim and Vianney Perchet
We study the prophet inequality, a fundamental problem in online decision-making and optimal stopping, in a practical setting where rewards are observed only through noisy realizations and reward distributions are unknown. At each stage, the decision-maker receives a noisy reward whose true value follows a linear model with an unknown latent parameter, and observes a feature vector drawn from a distribution. To address this challenge, we propose
algorithms that integrate learning and decision-making via lower-confidence-bound (LCB) thresholding. In the i.i.d.\ setting, we establish that both an Explore-then-Decide strategy and an $\varepsilon$-Greedy variant achieve the sharp competitive ratio of $1 - 1/e$, under a mild condition on the optimal value. For non-identical distributions, we show that a competitive ratio of $1/2$ can be guaranteed against a relaxed
benchmark. Moreover, with limited window access to past rewards, the tight ratio of $1/2$ against the optimal
benchmark is achieved.
Read the full abstract ▾
Machine Learning
Bridging Deep Learning and Integer Linear Programming: A Predictive-to-Prescriptive Framework for Supply Chain Analytics
Khai Banh Nghiep, Duc Nguyen Minh and Lan Hoang Thi
Although demand
forecasting is a critical component of supply chain planning, actual retail data can exhibit irreconcilable seasonality, irregular spikes, and noise, rendering precise projections nearly unattainable. This paper proposes a three-step analytical framework that combines
forecasting and operational analytics. The first stage consists of exploratory data analysis, where delivery-tracked data from 180,519 transactions are partitioned, and long-term trends, seasonality, and delivery-related attributes are examined. Secondly, the
forecasting performance of a statistical time series decomposition model N-BEATS MSTL and a recent deep learning architecture N-HiTS were compared. N-BEATS and N-HiTS were both statistically, and hence were N-BEATS's and N-HiTS's statistically selected. Most recent time series deep learning models, N-HiTS, N-BEATS. N-HiTS and N-BEATS N-HiTS and N-HiTS outperformed the statistical
benchmark to a large extent. N-BEATS was selected to be the most optimized model, as the one with the lowest
forecasting error, in the 3rd and final stage
forecasting values of the next 4 weeks of 1918 units, and provided those as a model with a set of deterministically integer linear program outcomes that are aimed to minimize the total delivery time with a set of bound budget, capacity, and service constraints. The solution allocation provided a feasible and cost-optimal shipping plan. Overall, the study provides a compelling example of the practical impact of precise
forecasting and simple, highly interpretable model optimization in logistics.
Read the full abstract ▾